This study develops a jurisprudential, algorithmic, and systems framework for automated regulatory intelligence within the structurally fragmented administrative environment of the United States. Mechanical and HVAC regulation is used as a test domain because a single field operation may simultaneously implicate federa...
Kostiantyn Pavroz· Metaverse Science, Society a...· 0 citations
This study examines how the rapid expansion of generative artificial intelligence (AI)
challenges traditional copyright law by shifting legal concerns beyond authorship
and ownership toward transparency, disclosure, traceability, and accountability in
AI-assisted artistic production.The study adopts a doctrinal and com...
Blegina Hasko Bezo· JUS & JUSTICIA· 0 citations
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages may require different capabilities, yet conventional joint t...
Rui Shi, Xunjian Yin, Jiacheng Sang et al.· 0 citations
This work proposes WSR-Tune, a Weight Space Reparameterization-based fine-tuning framework that preserves safety during downstream adaptation and achieves a more favorable trade-off between downstream performance and safety retention, demonstrating its effectiveness for reliable LLM fine-tuning.
Minsu Kim, Jongbok Won, Jeesup Park et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Diffusion Transformers (DiTs) deliver high-fidelity image and video generation, but inference requires many sequential model evaluations. Two acceleration strategies are increasingly important: model compression makes each evaluation cheaper, while adaptive inference avoids selected teacher computation through reuse, f...
Shuai-Qi Cheng, Jia-Hao Zhang, Bo-Yuan Gu et al.· 0 citations
This work investigates a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification and shows that this workflow robustly outperformed any manually engineered solutions.
Matthias Eder, Pantelis Emmanouil, V. Farias et al.· 0 citations
falcon{}, a counterexample-grounded verification framework that separates attack exploration from behavioral verification and connects them through execution traces of the program under test, is introduced, suggesting that execution-grounded feedback can mitigate reward overoptimization while preserving useful guidance...
Tue Le, A. N. Hoang, Gabriel Sasseville et al.· 0 citations
MC-LDM represents the first diffusion-based framework to leverage multimodal priors for MRI forecasting, and enables patient-specific trajectory generation that captures aspects of AD heterogeneity not observable from structural anatomy alone, bridging the gap between rich multimodal supervision and the strict constrai...
Antonio Scardace, Silvia Ingala, S. Battiato et al.· 0 citations
We present Stable Signer V3, an interactive high-resolution sign language avatar system built on 4D Deformable Primitive Splatting. It addresses three limitations of existing avatars: restricted facial expression, inaccurate identity-specific body deformation, and loss of fine appearance details. Shared Face Primitive...
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer integrates multi-step reasoning, reliable tool use and failure recovery into a single model that runs locally on consumer devices without r...
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed et al.· 0 citations
We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to select matching intervals. This lets users interact with avatars for local editing and motion inspection. However, making these selections with existing la...
Junsu Kim, N. Kim, Dongyoon Han et al.· 0 citations
Location encoders learn compact representations of latitude--longitude coordinates for downstream geospatial prediction tasks. Existing approaches are pretrained using continuous or naturally occurring supervision, such as imagery, climate variables, or species distributions, and therefore do not explicitly capture adm...
